Abstract: A computer-implemented method and a computing system are provided for training a matting neural network to generate mattes for creating portraits to be used on identity documents. The matting neural network is trained by using standardized images conforming to a template which prescribes that each standardized image should depict a human face. A standardized image is obtained by adjusting an input image which includes an area representing a face of the person and was, e.g., taken with a camera, so that a relationship between the size of the adjusted input image and the distance between target points (which represent parts of the person) in the adjusted input image satisfies a condition determined by the template, and in the adjusted input image the area is in a position defined by the template.

Abstract: Systems and methods for sealing a document using a visible graphical digital seal are described, as well as systems and methods for authenticating a sealed document by identifying and decoding the digital seal.

Abstract: Methods and systems for authenticating identity credentials are provided. An identity credential is proofed and issued with biometric and enrollment data, as well as a graphical seal. The identity credential is later presented for authentication, and the seal is used to access the biometric and enrollment data. Live biometric and identification data are compared to the identity credential, and the identity credential may be authenticated.

Abstract: A system for authenticating a subject identification document includes instructions causing a processor to receive a first image of the document, depicting, in RGB color space, the document illuminated by UV light, and transform the first image to a second image in YCbCr color space. The instructions cause the processor to divide the second image into regions of interest (ROIs), and, for each ROI, generate a color profile descriptor including first data elements associated with pixel color in the YCbCr color space, and second data elements associated with pixel intensity of pixels within the ROI. The instructions also cause the processor to generate a score for the second image based on a comparison of the color profile descriptor for each ROI to a corresponding ROI of an enrolled document template, and compare the score to a threshold to determine whether the document is authenticated.

Abstract: A system for authenticating a subject identification document includes a memory section storing computer-executable instructions and a memory section storing an enrolled document template, ROI information, and a codebook representing partitions of a [Cb, Cr] color plane. The system includes a processor in communication with the memory. The processor executes the instructions that, when executed, cause the processor to receive an image of the document, the image depicting, in a RGB color space, the document. The processor transforms the image of the document to a second image of the document in a YCbCr color space. The processor assigns pixels within a ROI in the second image corresponding to the ROI information to the partitions of the codebook. The processor generates a template based on respective counts of the pixels assigned to the partitions of the codebook. The processor compares the template to the enrolled document template to authenticate document.

Abstract: An authentication processing system includes a memory storing a portrait fraud detection application, and a processing unit coupled with the memory and configured to execute the portrait fraud detection application. The portrait fraud detection application, when executed, configures the processing unit to receive a capture of a document including a portrait photo and at least one overlay, detect a face in the portrait photo among the at least one overlay in the capture, and determine the portrait photo is fraudulent; and initiate an indication the document is fraudulent.

Abstract: Techniques for texture-based authentication of digital identity documents are disclosed. The disclosed techniques include authentication based on global texture information and/or on local texture information. Global texture-based authentication may include generating a global texture profile for an identity document image and comparing the global texture profile with a stored profile associated with a jurisdiction class of the identity document. Local texture-based authentication may include generating one or more local texture patches representative of texture information of one or more select local blocks of the ID. The one or more local texture patches are provided as input to one or more local detectors each trained to detect the presence of a forgery based on a target manipulation space.

Abstract: A system for authenticating a user includes a memory device, and a processor. The processor is configured to receive a first biometric sample associated with a user from a biometric measurement device, and receive, substantially contemporaneously with receiving the first biometric sample, an image of a user credential, where the image includes credential data, such as any of a variety of personally identifiable information. The processor may also be configured to compare the received first biometric sample to at least one of: i) a second biometric sample included in the credential data, or ii) a third biometric sample stored by an authentication database in association with the user. Likewise, in at least some embodiments, the processor may determine whether to authenticate the user, such as based upon the comparison.

Abstract: Techniques for texture-based authentication of digital identity documents are disclosed. The disclosed techniques include authentication based on global texture information and/or on local texture information. Global texture-based authentication may include generating a global texture profile for an identity document image and comparing the global texture profile with a stored profile associated with a jurisdiction class of the identity document. Local texture-based authentication may include generating one or more local texture patches representative of texture information of one or more select local blocks of the ID. The one or more local texture patches are provided as input to one or more local detectors each trained to detect the presence of a forgery based on a target manipulation space.

Abstract: In general, the subject matter described in this specification relates to security credentials for documents, such as identification documents. One example is an identification document that includes a photographic image of an individual associated with the document, and a spiral pattern applied to a region of the identification document. The spiral pattern includes an elliptical spiral segmented into a plurality of arc segments, where wherein the arc segments of the spiral pattern encode identification data associated with the individual. Other implementations include corresponding processes, systems, apparatus, and computer programs related to generating and verifying identification documents with spiral patterns.

Abstract: Some implementations of the present disclosure are directed to a computer-implemented method that includes: detecting a plurality of characters from a photo of an object; generating a set of character-based features based on the plurality of characters; matching the set of character-based features with a template of feature sets obtained from known objects; based on a matching set of character-based features, establishing a matching transformation between the object in the photo and the template of feature sets; and projecting the matching transformation to the photo such that the object is segmented from the photo.

Abstract: Methods and systems, including computer programs encoded on a computer storage medium, are used for generating an identification document comprising an image of an individual, personal information associated with the individual, and line patterns that include multiple distinct square-wave lines. The square-wave lines enable credential data about a person assigned to the identification document to be securely stored at the identification document. A first portion of distinct square-wave lines are used to encode a first item of credential data and to determine whether the image of the individual corresponds to the first item of credential data. A second portion of distinct square-wave lines are used to encode a second item of credential data and to determine whether the personal information corresponds to the second item of credential data.

Abstract: Some implementations provide a computer-assisted method for embedding information in an identification document. The method includes: modulating information by varying lengths of line segments; generating a line code that includes the line segments with corresponding lengths; and applying the line code on an identification document such that the information is used to authenticate the identification document as genuine when a person presents the identification document to verify an identify of the person.

Abstract: In general, the subject matter described in this specification relates to security credentials for documents, such as identification documents. One example is an identification document that includes a photographic image of an individual associated with the document, and a spiral pattern applied to a region of the identification document. The spiral pattern includes an elliptical spiral segmented into a plurality of arc segments, where wherein the arc segments of the spiral pattern encode identification data associated with the individual. Other implementations include corresponding processes, systems, apparatus, and computer programs related to generating and verifying identification documents with spiral patterns.

Abstract: Image data is obtained. The image data is divided into a plurality of segments. A frequency spectrum is generated for each segment. One or more dominant signals corresponding to the image data are estimated for each segment based on the associated frequency spectrum. A coherent enhancement process is applied to the one or more dominant signals in each segment by performing sequential scanning in one or more directions. For each of the one or more dominant signals, the data resulting from the coherent enhancement of the signal are stored into separate image buffers, wherein an image buffer is configured to store data resulting from the coherent enhancement of the associated dominant signal across multiple segments. Each of the one or more dominant signals are reconstructed based on aggregating the data stored in a corresponding image buffer.

Abstract: A method includes: normalizing intensities at each pixel in a fingerprint slap scan image such that variations of pixel intensities between fingerprint ridges and valleys are regularized; subsequently dividing the fingerprint slap scan image into blocks of pixels; for each block of pixels, estimating a spatial separation between adjacent fingerprint ridges as well as a ridge orientation for each fingerprint ridge within the particular block of pixels; calculating a distortion map for the various blocks by projecting, according to the estimated ridge orientation for each fingerprint ridge, an adjustment to the estimated spatial separation that is based on a difference between the estimated spatial separation and a target spatial separation; and warping the fingerprint slap scan image to compensate for the calculated distortion map such that the fingerprint ridges in the warped fingerprint slap scan image are scaled to compensate for local variations of adjustments in the calculated distortion map.

Abstract: A computer-implemented method that includes: accessing data encoding a fingerprint slap scan image, the fingerprint slap scan image including fingerprints of a number of fingers from a subject's hand; performing a radon transform of the fingerprint slap scan image to generate a sinogram, the sinogram represented on a grid having a lateral span axis and a projection angle axis; automatically identifying patterns of segments on the sinogram as finger lines, each finger lines corresponding to a particular finger present on the fingerprint slap scan image; and based on identified finger lines on the sinogram, automatically determining whether one or more fingers are missing on the fingerprint slap scan image.